© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 10613
    Prev
    Next
    INDEX
    Explanations

    specific visual components and elements in descriptions, particularly in the context of art or design

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Preceding descriptive words

    np_acts-logits-general · gemini-2.0-flash

    "this" / "the" / "a"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ſch
    -0.68
     eſſ
    -0.66
     faſt
    -0.66
     ſche
    -0.66
     poffible
    -0.62
     viſ
    -0.59
     ſta
    -0.57
     lenker
    -0.57
     tranſ
    -0.57
     Majefty
    -0.56
    POSITIVE LOGITS
     view
    0.39
     Behind
    0.36
    twimg
    0.36
    ➋
    0.35
     dug
    0.35
     check
    0.34
     looking
    0.34
     View
    0.34
     showing
    0.34
     angeb
    0.33
    Activations Density 0.148%

    No Known Activations